A Benchmarking Study of Embedding-based Entity Alignment for Knowledge Graphs

Abstract

Entity alignment seeks to find entities in different knowledge graphs (KGs) that refer to the same real-world object. Recent advancement in KG embedding impels the advent of embedding-based entity alignment, which encodes entities in a continuous embedding space and measures entity similarities based on the learned embeddings. In this paper, we conduct a comprehensive experimental study of this emerging field. We survey 23 recent embedding-based entity alignment approaches and categorize them based on their techniques and characteristics. We also propose a new KG sampling algorithm, with which we generate a set of dedicated benchmark datasets with various heterogeneity and distributions for a realistic evaluation. We develop an open-source library including 12 representative embedding-based entity alignment approaches, and extensively evaluate these approaches, to understand their strengths and limitations. Additionally, for several directions that have not been explored in current approaches, we perform exploratory experiments and report our preliminary findings for future studies. The benchmark datasets, open-source library and experimental results are all accessible online and will be duly maintained.

Accepted in the 46th International Conference on Very Large Data Bases (VLDB 2020)

References in corpus (25)

• Semi-Supervised Classification with Graph Convolutional Networks
• A Survey on Knowledge Graphs: Representation, Acquisition and Applications
• Spectral Networks and Locally Connected Networks on Graphs
• Complex Embeddings for Simple Link Prediction
• A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Network
• RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space
• TuckER: Tensor Factorization for Knowledge Graph Completion
• Knowledge Graph Embedding for Link Prediction: A Comparative Analysis
• SimplE Embedding for Link Prediction in Knowledge Graphs
• Representation Learning on Graphs: Methods and Applications
• REGAL: Representation Learning-based Graph Alignment
• Analogical Inference for Multi-Relational Embeddings
• ProjE: Embedding Projection for Knowledge Graph Completion
• Learning to Exploit Long-term Relational Dependencies in Knowledge Graphs
• PARIS: Probabilistic Alignment of Relations, Instances, and Schema
• Unsupervised Hyperalignment for Multilingual Word Embeddings
• Analyzing the Limitations of Cross-lingual Word Embedding Mappings
• Cross-lingual Entity Alignment via Joint Attribute-Preserving Embedding
• SiGMa: Simple Greedy Matching for Aligning Large Knowledge Bases
• Knowledge Representation Learning: A Quantitative Review
• Multi-view Knowledge Graph Embedding for Entity Alignment
• Knowledge Graph Alignment Network with Gated Multi-hop Neighborhood Aggregation
• Multi-Channel Graph Neural Network for Entity Alignment
• Realistic Re-evaluation of Knowledge Graph Completion Methods: An Experimental Study
• Jointly Learning Entity and Relation Representations for Entity Alignment

Cited by in corpus (30)

• A Survey on Knowledge Graphs: Representation, Acquisition and Applications
• Construction of Knowledge Graphs: State and Challenges
• Time-aware Graph Neural Networks for Entity Alignment between Temporal Knowledge Graphs
• Unsupervised Entity Alignment for Temporal Knowledge Graphs
• ClusterEA: Scalable Entity Alignment with Stochastic Training and Normalized Mini-batch Similarities
• End-to-End Entity Resolution for Big Data: A Survey
• LargeEA: Aligning Entities for Large-scale Knowledge Graphs
• Informed Multi-context Entity Alignment
• Large-scale Entity Alignment via Knowledge Graph Merging, Partitioning and Embedding
• Entity Alignment with Reliable Path Reasoning and Relation-Aware Heterogeneous Graph Transformer
• SEA: A Scalable Entity Alignment System
• HiPrompt: Few-Shot Biomedical Knowledge Fusion via Hierarchy-Oriented Prompting
• High-quality Task Division for Large-scale Entity Alignment
• Combating Confirmation Bias: A Unified Pseudo-Labeling Framework for Entity Alignment
• PRASEMap: A Probabilistic Reasoning and Semantic Embedding based Knowledge Graph Alignment System
• EAGER: Embedding-Assisted Entity Resolution for Knowledge Graphs
• OntoEA: Ontology-guided Entity Alignment via Joint Knowledge Graph Embedding
• Cross-lingual Entity Alignment with Incidental Supervision
• Unsupervised Knowledge Graph Alignment by Probabilistic Reasoning and Semantic Embedding
• Towards Entity Alignment in the Open World: An Unsupervised Approach
• OWL2Vec*: Embedding of OWL Ontologies
• Orphan Articles: The Dark Matter of Wikipedia
• CollaborER: A Self-supervised Entity Resolution Framework Using Multi-features Collaboration
• A Critical Assessment of State-of-the-Art in Entity Alignment
• A Comparative Study on Structural and Semantic Properties of Sentence Embeddings
• Knowing the No-match: Entity Alignment with Dangling Cases
• An Industry Evaluation of Embedding-based Entity Alignment
• Principled Representation Learning for Entity Alignment
• Unsupervised Entity Alignment Based on Personalized Discriminative Rooted Tree
• Link Prediction or Perdition: the Seeds of Instability in Knowledge Graph Embeddings